DSFDcd: Joint Distribution Sampling and Feature Decoupling Deep Network for Remote Sensing Change Detection
文献类型：期刊论文
| 作者 | Wang, Bin1,2; Jiang, Xiaohu1,2; Qin, Pinle1; Zeng, Jianchao1 |
| 刊名 | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
 |
| 出版日期 | 2025 |
| 卷号 | 63页码:5631312 |
| 关键词 | Feature extraction Prototypes Training Computational modeling Transformers Semantics Data models Generators Data mining Vegetation mapping Change detection distribution sampling exceed-expectation (EE) loss feature decoupling |
| ISSN号 | 0196-2892 |
| DOI | 10.1109/TGRS.2025.3585229 |
| 产权排序 | 2 |
| 文献子类 | Article |
| 英文摘要 | Remote sensing change detection (RSCD) aims to identify the regions of interest that have changed between dual-temporal images. However, most deep models predict CD results by extracting multiscale hybrid features, which could easily lead to ambiguous semantic boundaries; in addition, the existing feature acquisition tends to lack consideration of capturing their diversity, usually causing poor model generalization. Thus, this article decomposes the mixed features into change and invariant features jointly with stochastic distribution sampling and convolution, thus accomplishing robust RSCD based on decoupled representations. In the training stage, the posterior distribution of the uncoupled features is first learned through label calibration to train the prior distribution generator; then, robust feature decoupling is implemented combining the convolutional feature separator with reparameterized sampling over the decoupled posteriori distribution, and further aggregating the decoupled features through prototype learning; finally, the exceed-expectation (EE) loss regularizer is proposed to push or pull these positive and negative sample features to a more distant end, thereby increasing the interclass distance by boosting the predicted expectation. In the testing stage, the robust RSCD based on decoupled representation is accomplished through the feature separator, decoupled prior distribution random sampling, and the CD head without posterior distribution support. Experiments prove that DSFDcd has achieved remarkable results in terms of qualitative and quantitative metrics. Our codes will be available at https://github.com/iceking111/DSFDcd |
| URL标识 | 查看原文 |
| WOS关键词 | PROTOTYPE |
| WOS研究方向 | Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:001530269200011 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/215421]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 通讯作者 | Qin, Pinle |
| 作者单位 | 1.North Univ China, Dept Comp Sci & Technol, Taiyuan 030051, Peoples R China; 2.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wang, Bin,Jiang, Xiaohu,Qin, Pinle,et al. DSFDcd: Joint Distribution Sampling and Feature Decoupling Deep Network for Remote Sensing Change Detection[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2025,63:5631312. |
| APA | Wang, Bin,Jiang, Xiaohu,Qin, Pinle,&Zeng, Jianchao.(2025).DSFDcd: Joint Distribution Sampling and Feature Decoupling Deep Network for Remote Sensing Change Detection.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,63,5631312. |
| MLA | Wang, Bin,et al."DSFDcd: Joint Distribution Sampling and Feature Decoupling Deep Network for Remote Sensing Change Detection".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 63(2025):5631312. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。